© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 651
    Prev
    Next
    INDEX
    Explanations

    data, information, attendance, humanity, equilibrium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     F
    1.24
     G
    1.20
     S
    1.20
     T
    1.12
     N
    1.09
     H
    1.08
     J
    1.06
     O
    0.98
     E
    0.97
     M
    0.93
    POSITIVE LOGITS
     antidote
    1.59
    粑
    1.48
     방식으로
    1.42
    蒡
    1.40
    ](\
    1.39
     기능을
    1.38
     그렇게
    1.37
    waveform
    1.37
     cadmium
    1.35
    getCQL
    1.34
    Activations Density 0.405%

    No Known Activations